🐴 Gulltoppr MCP server
io.github.portdeveloper/gulltopprportdeveloperstreamable-httpv0.1.2Scanned
Resolve any EVM contract ABI (even unverified, via decompilation), read, simulate, prepare txs.
12 tools: 1 do something that can't be undone, 4 change things and 7 only read.
- Reads private data · 0
- Reads text others write · 12
- Can send data out · 1
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the 🐴 Gulltoppr MCP server can do
The 🐴 Gulltoppr MCP server is published by the GitHub account portdeveloper. It has 12 tools. It can do things that cannot be undone, such as sending, paying or publishing (simulate) and create or change data (4 tools: read_contract, encode_call, prepare_tx and decode_tx), but cannot delete data. 7 tools only read.
12 tools bring in text other people can write (list_chains, runtime_metrics, lookup_selector and 9 more); 1 tool can send data out of your system (simulate).
The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 0.1.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
12 tools
Can't be undone 1Claude Code: ask
simulateSimulate a call and return success, gas, decoded return, and best-effort state diff / asset changes / logs.Reads text others writeCan send data out1 finding
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "simulate" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
Description, as the server wrote it Simulate a call and return success, gas, decoded return, and best-effort state diff / asset changes / logs. Provide a high-level call (address + function + args) or raw (to + data), never both.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Changes things 4Claude Code: ask
decode_txDecode what a transaction did: delegated heimdall decode plus `decoded_call` from the resolved target ABI when available.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Decode what a transaction did: delegated heimdall decode plus `decoded_call` from the resolved target ABI when available. Prefer `decoded_call` for typed function/arg names, and read its provenance.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
encode_callEncode a function call to calldata (0x…) without sending anything.Reads text others write1 finding
Why it is in this group
- The name "encode_call" says "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "encode_call" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "encode_call" says "call": a word for a change.
Description, as the server wrote it Encode a function call to calldata (0x…) without sending anything.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
prepare_txPrepare a contract WRITE for the user to sign.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Prepare a contract WRITE for the user to sign. Returns an UNSIGNED transaction, its simulation, a human-readable summary, safety metadata, warnings, a configured signing deeplink, and an EIP-1193 wallet request when signing is recommended. IMPORTANT: this tool NEVER signs or broadcasts. Present the summary + simulation + warnings to the user. Only hand them the `deeplink` or `wallet_request` when `safety.signing_recommended` is true. If `safety.risk_level` is high or blocked, make that explicit; blocked means do not send.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
read_contractCall a view/pure function and get the decoded result.Reads text others write1 finding
Why it is in this group
- The name "read_contract" says "read": a word for reading.
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "read_contract" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "read_contract" says "read": a word for reading.
Description, as the server wrote it Call a view/pure function and get the decoded result. No wallet, no cost. Rejects state-mutating functions.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Only reads 7Show 7 read-only tools
export_registryReturn the CC0 selector commons as NDJSON.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Return the CC0 selector commons as NDJSON. This can be large; prefer lookup_selector for normal agent workflows.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
list_chainsList viem-backed chain aliases and ids.Reads text others writeNo findings
Why it is in this group
- The name "list_chains" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List viem-backed chain aliases and ids. Use filters to find testnets, default-RPC chains, or a named chain before resolving contracts.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
lookup_selectorLookup gulltoppr-proven signatures for a 4-byte function/error selector or 32-byte event topic0.Reads text others writeNo findings
Why it is in this group
- The name "lookup_selector" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Lookup gulltoppr-proven signatures for a 4-byte function/error selector or 32-byte event topic0. Prefer these over public 4byte guesses.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
registry_statsRead selector commons counts by proof grade and bytecode-match index size.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read selector commons counts by proof grade and bytecode-match index size.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
resolve_abiResolve a contract's interface from chain + address via a fallback ladder (Etherscan → Sourcify → proxy → heimdall decompile → 4byte).Reads text others writeNo findings
Why it is in this group
- The name "resolve_abi" says "resolve": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Resolve a contract's interface from chain + address via a fallback ladder (Etherscan → Sourcify → proxy → heimdall decompile → 4byte). Returns a compact capability manifest (read vs write functions, the 'buttons'), proxy chain, token metadata, and PROVENANCE. ALWAYS read `provenance`: a `decompiled` ABI has synthetic function names — treat it with care and confirm intent before writing. Partial, proxy, and bytecode-match results lead with a WARNING before the JSON. The compact manifest/provenance is also returned as structuredContent. Use method_q/method_kind/method_limit for large ABIs. Raw ABI is omitted from MCP output to save tokens; use REST/SDK resolve_abi with include_abi=true if needed.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
resolve_nameResolve an ENS/Basename to an address, or an address to its primary ENS/Basename.Reads text others writeNo findings
Why it is in this group
- The name "resolve_name" says "resolve": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Resolve an ENS/Basename to an address, or an address to its primary ENS/Basename. Pass chain=base for Basenames.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
runtime_metricsRead process-local resolver/rung/RPC counters for smoke checks and reliability dashboards.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read process-local resolver/rung/RPC counters for smoke checks and reliability dashboards.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write12
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:09 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (1 irreversible, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.gulltoppr.dev/mcp: tools/list returned 12 tools to an anonymous client, including simulate (irreversible), read_contract (write), encode_call (write), prepare_tx (write), decode_tx (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnread_contract
The server marks "read_contract" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "read_contract" says "read": a word for reading.
- Warnencode_call
The server marks "encode_call" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "encode_call" says "call": a word for a change.
- Warnsimulate
The server marks "simulate" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http gulltoppr https://mcp.gulltoppr.dev/mcpclaude mcp add --transport http gulltoppr https://mcp.gulltoppr.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__gulltoppr__list_chains",
"mcp__gulltoppr__runtime_metrics",
"mcp__gulltoppr__lookup_selector",
"mcp__gulltoppr__registry_stats",
"mcp__gulltoppr__export_registry",
"mcp__gulltoppr__resolve_abi",
"mcp__gulltoppr__resolve_name"
],
"ask": [
"mcp__gulltoppr__read_contract",
"mcp__gulltoppr__encode_call",
"mcp__gulltoppr__simulate",
"mcp__gulltoppr__prepare_tx",
"mcp__gulltoppr__decode_tx"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as gulltoppr. Review it before you use it.
Capability tags behind 12 rules
- mcp__gulltoppr__list_chains untrusted-input
- mcp__gulltoppr__runtime_metrics untrusted-input
- mcp__gulltoppr__lookup_selector untrusted-input
- mcp__gulltoppr__registry_stats untrusted-input
- mcp__gulltoppr__export_registry untrusted-input
- mcp__gulltoppr__resolve_abi untrusted-input
- mcp__gulltoppr__read_contract untrusted-input
- mcp__gulltoppr__encode_call untrusted-input
- mcp__gulltoppr__simulate untrusted-input, outbound
- mcp__gulltoppr__prepare_tx untrusted-input
- mcp__gulltoppr__decode_tx untrusted-input
- mcp__gulltoppr__resolve_name untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.portdeveloper/gulltoppr/verify?hash=b19c214f7daa9a649e4156963a9c66941ff48609147d97978cf73f31690764cc" | jq -e '.changed == false'Pinned hash b19c214f7daa, from Nov 20, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.portdeveloper/gulltoppr/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.portdeveloper/gulltoppr)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:45 UTC.
🐴 Gulltoppr MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the 🐴 Gulltoppr MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 5 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the 🐴 Gulltoppr MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the 🐴 Gulltoppr MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: simulate.
What tools does the 🐴 Gulltoppr MCP server have?
- 12 tools: 1 irreversible, 4 write, 7 read. simulate, read_contract, encode_call, prepare_tx, decode_tx, list_chains, runtime_metrics, lookup_selector and 4 more.
Does the 🐴 Gulltoppr MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the 🐴 Gulltoppr MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): simulate.
Has the 🐴 Gulltoppr MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.